yt_dlp/extractor/steam.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     extract_attributes,
   8     ExtractorError,
   9     get_element_by_class,
  10 )
  11
  12
  13 class SteamIE(InfoExtractor):
  14     _VALID_URL = r"""(?x)
  15         https?://(?:store\.steampowered|steamcommunity)\.com/
  16             (?:agecheck/)?
  17             (?P<urltype>video|app)/ #If the page is only for videos or for a game
  18             (?P<gameID>\d+)/?
  19             (?P<videoID>\d*)(?P<extra>\??) # For urltype == video we sometimes get the videoID
  20         |
  21         https?://(?:www\.)?steamcommunity\.com/sharedfiles/filedetails/\?id=(?P<fileID>[0-9]+)
  22     """
  23     _VIDEO_PAGE_TEMPLATE = 'http://store.steampowered.com/video/%s/'
  24     _AGECHECK_TEMPLATE = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970'
  25     _TESTS = [{
  26         'url': 'http://store.steampowered.com/video/105600/',
  27         'playlist': [
  28             {
  29                 'md5': '695242613303ffa2a4c44c9374ddc067',
  30                 'info_dict': {
  31                     'id': '256785003',
  32                     'ext': 'mp4',
  33                     'title': 'Terraria video 256785003',
  34                     'thumbnail': r're:^https://cdn\.[^\.]+\.steamstatic\.com',
  35                     'n_entries': 2,
  36                 }
  37             },
  38             {
  39                 'md5': '6a294ee0c4b1f47f5bb76a65e31e3592',
  40                 'info_dict': {
  41                     'id': '2040428',
  42                     'ext': 'mp4',
  43                     'title': 'Terraria video 2040428',
  44                     'playlist_index': 2,
  45                     'thumbnail': r're:^https://cdn\.[^\.]+\.steamstatic\.com',
  46                     'n_entries': 2,
  47                 }
  48             }
  49         ],
  50         'info_dict': {
  51             'id': '105600',
  52             'title': 'Terraria',
  53         },
  54         'params': {
  55             'playlistend': 2,
  56         }
  57     }, {
  58         'url': 'https://store.steampowered.com/app/271590/Grand_Theft_Auto_V/',
  59         'info_dict': {
  60             'id': '256757115',
  61             'title': 'Grand Theft Auto V video 256757115',
  62             'ext': 'mp4',
  63             'thumbnail': r're:^https://cdn\.[^\.]+\.steamstatic\.com',
  64             'n_entries': 20,
  65         },
  66     }]
  67
  68     def _real_extract(self, url):
  69         m = self._match_valid_url(url)
  70         fileID = m.group('fileID')
  71         if fileID:
  72             video_url = url
  73             playlist_id = fileID
  74         else:
  75             gameID = m.group('gameID')
  76             playlist_id = gameID
  77             video_url = self._VIDEO_PAGE_TEMPLATE % playlist_id
  78
  79         self._set_cookie('steampowered.com', 'wants_mature_content', '1')
  80         self._set_cookie('steampowered.com', 'birthtime', '944006401')
  81         self._set_cookie('steampowered.com', 'lastagecheckage', '1-0-2000')
  82
  83         webpage = self._download_webpage(video_url, playlist_id)
  84
  85         if re.search('<div[^>]+>Please enter your birth date to continue:</div>', webpage) is not None:
  86             video_url = self._AGECHECK_TEMPLATE % playlist_id
  87             self.report_age_confirmation()
  88             webpage = self._download_webpage(video_url, playlist_id)
  89
  90         videos = re.findall(r'(<div[^>]+id=[\'"]highlight_movie_(\d+)[\'"][^>]+>)', webpage)
  91         entries = []
  92         playlist_title = get_element_by_class('apphub_AppName', webpage)
  93         for movie, movie_id in videos:
  94             if not movie:
  95                 continue
  96             movie = extract_attributes(movie)
  97             if not movie_id:
  98                 continue
  99             entry = {
 100                 'id': movie_id,
 101                 'title': f'{playlist_title} video {movie_id}',
 102             }
 103             formats = []
 104             if movie:
 105                 entry['thumbnail'] = movie.get('data-poster')
 106                 for quality in ('', '-hd'):
 107                     for ext in ('webm', 'mp4'):
 108                         video_url = movie.get('data-%s%s-source' % (ext, quality))
 109                         if video_url:
 110                             formats.append({
 111                                 'format_id': ext + quality,
 112                                 'url': video_url,
 113                             })
 114             self._sort_formats(formats)
 115             entry['formats'] = formats
 116             entries.append(entry)
 117         embedded_videos = re.findall(r'(<iframe[^>]+>)', webpage)
 118         for evideos in embedded_videos:
 119             evideos = extract_attributes(evideos).get('src')
 120             video_id = self._search_regex(r'youtube\.com/embed/([0-9A-Za-z_-]{11})', evideos, 'youtube_video_id', default=None)
 121             if video_id:
 122                 entries.append({
 123                     '_type': 'url_transparent',
 124                     'id': video_id,
 125                     'url': video_id,
 126                     'ie_key': 'Youtube',
 127                 })
 128         if not entries:
 129             raise ExtractorError('Could not find any videos')
 130
 131         return self.playlist_result(entries, playlist_id, playlist_title)